developer_uid: Hastagaras
submission_id: hastagaras-lm3-8b-lightune_v1
model_name: hastagaras-lm3-8b-lightune_v1
model_group: Hastagaras/lm3-8b-lightu
status: torndown
timestamp: 2024-05-09T03:54:56+00:00
num_battles: 9383
num_wins: 4980
celo_rating: 1183.67
family_friendly_score: 0.0
submission_type: basic
model_repo: Hastagaras/lm3-8b-lightune
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/reward_gpt2_medium_preference_24m_e2
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: hastagaras-lm3-8b-lightune_v1
is_internal_developer: False
language_model: Hastagaras/lm3-8b-lightune
model_size: 8B
ranking_group: single
us_pacific_date: 2024-05-08
win_ratio: 0.5307470958115741
generation_params: {'temperature': 0.8, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou're `{bot_name}` in this Roleplay. Gestures and other non-verbal actions are written between asterisks (*).\n\nYour persona as {bot_name}: {memory}\n\n", 'prompt_template': 'Your message example: {bot_name}: {prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
model_eval_status: success
Resubmit model
Running pipeline stage MKMLizer
Starting job with name hastagaras-lm3-8b-lightune-v1-mkmlizer
Waiting for job on hastagaras-lm3-8b-lightune-v1-mkmlizer to finish
hastagaras-lm3-8b-lightune-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║     _____            __           __                                ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║       /___/                                                         ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║  Version: 0.8.10                                                    ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║  belonging to:                                                      ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║  Chai Research Corp.                                                ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ║                                                                     ║
hastagaras-lm3-8b-lightune-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
hastagaras-lm3-8b-lightune-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
hastagaras-lm3-8b-lightune-v1-mkmlizer:   warnings.warn(warning_message, FutureWarning)
hastagaras-lm3-8b-lightune-v1-mkmlizer: Downloaded to shared memory in 26.932s
hastagaras-lm3-8b-lightune-v1-mkmlizer: quantizing model to /dev/shm/model_cache
hastagaras-lm3-8b-lightune-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
hastagaras-lm3-8b-lightune-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:  32%|███▏      | 93/291 [00:01<00:02, 92.20it/s]
Loading 0:  65%|██████▍   | 188/291 [00:02<00:01, 93.65it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 29.49it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
hastagaras-lm3-8b-lightune-v1-mkmlizer: quantized model in 18.957s
hastagaras-lm3-8b-lightune-v1-mkmlizer: Processed model Hastagaras/lm3-8b-lightune in 46.854s
hastagaras-lm3-8b-lightune-v1-mkmlizer: creating bucket guanaco-mkml-models
hastagaras-lm3-8b-lightune-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
hastagaras-lm3-8b-lightune-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v1
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v1/special_tokens_map.json
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v1/config.json
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v1/tokenizer_config.json
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v1/tokenizer.json
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/hastagaras-lm3-8b-lightune-v1/flywheel_model.0.safetensors
hastagaras-lm3-8b-lightune-v1-mkmlizer: loading reward model from ChaiML/reward_gpt2_medium_preference_24m_e2
hastagaras-lm3-8b-lightune-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-lm3-8b-lightune-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-lightune-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-lm3-8b-lightune-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-lightune-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
hastagaras-lm3-8b-lightune-v1-mkmlizer:   warnings.warn(
hastagaras-lm3-8b-lightune-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
hastagaras-lm3-8b-lightune-v1-mkmlizer:   return self.fget.__get__(instance, owner)()
hastagaras-lm3-8b-lightune-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
hastagaras-lm3-8b-lightune-v1-mkmlizer: Saving duration: 0.236s
hastagaras-lm3-8b-lightune-v1-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 4.128s
hastagaras-lm3-8b-lightune-v1-mkmlizer: creating bucket guanaco-reward-models
hastagaras-lm3-8b-lightune-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
hastagaras-lm3-8b-lightune-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v1_reward
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v1_reward/config.json
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v1_reward/special_tokens_map.json
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v1_reward/tokenizer_config.json
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v1_reward/vocab.json
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v1_reward/merges.txt
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v1_reward/tokenizer.json
hastagaras-lm3-8b-lightune-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/hastagaras-lm3-8b-lightune-v1_reward/reward.tensors
Job hastagaras-lm3-8b-lightune-v1-mkmlizer completed after 72.97s with status: succeeded
Stopping job with name hastagaras-lm3-8b-lightune-v1-mkmlizer
Pipeline stage MKMLizer completed in 76.91s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service hastagaras-lm3-8b-lightune-v1
Waiting for inference service hastagaras-lm3-8b-lightune-v1 to be ready
Inference service hastagaras-lm3-8b-lightune-v1 ready after 30.211925268173218s
Pipeline stage ISVCDeployer completed in 37.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.9760150909423828s
Received healthy response to inference request in 1.0065927505493164s
Received healthy response to inference request in 1.3408551216125488s
Received healthy response to inference request in 1.3308093547821045s
Received healthy response to inference request in 1.2908260822296143s
5 requests
0 failed requests
5th percentile: 1.063439416885376
10th percentile: 1.1202860832214356
20th percentile: 1.2339794158935546
30th percentile: 1.2988227367401124
40th percentile: 1.3148160457611084
50th percentile: 1.3308093547821045
60th percentile: 1.3348276615142822
70th percentile: 1.33884596824646
80th percentile: 1.4678871154785158
90th percentile: 1.7219511032104493
95th percentile: 1.8489830970764158
99th percentile: 1.9506086921691894
mean time: 1.3890196800231933
Pipeline stage StressChecker completed in 8.31s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.03s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
hastagaras-lm3-8b-lightune_v1 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
hastagaras-lm3-8b-lightune_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of hastagaras-lm3-8b-lightune_v1
Running pipeline stage ISVCDeleter
Checking if service hastagaras-lm3-8b-lightune-v1 is running
Tearing down inference service hastagaras-lm3-8b-lightune-v1
Toredown service hastagaras-lm3-8b-lightune-v1
Pipeline stage ISVCDeleter completed in 9.45s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-lightune-v1/config.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightune-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightune-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightune-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key hastagaras-lm3-8b-lightune-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key hastagaras-lm3-8b-lightune-v1_reward/config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key hastagaras-lm3-8b-lightune-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.19s
hastagaras-lm3-8b-lightune_v1 status is now torndown due to DeploymentManager action